Integrations
Temporal
Trace Temporal-orchestrated LLM workflows in Muster via OpenTelemetry instrumentation.
Temporal is a durable-execution platform that guarantees code execution despite failures. Muster captures Temporal-orchestrated LLM workflows via OpenTelemetry — useful for long-running agent runs that need to survive restarts.
Setup
%pip install temporalio openai openai-agents langfuse openinference-instrumentation-openai-agentsimport os
os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..."
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..."
os.environ["LANGFUSE_BASE_URL"] = "https://app.getmuster.io"
os.environ["OPENAI_API_KEY"] = "sk-proj-..."
os.environ["TEMPORAL_HOST"] = "localhost:7233"Enable instrumentation
from openinference.instrumentation.openai_agents import OpenAIAgentsInstrumentor
OpenAIAgentsInstrumentor().instrument()from langfuse import get_client
langfuse = get_client()
langfuse.auth_check()Workflow execution, LLM calls, costs, latencies, and failures all flow into Muster — making it possible to debug retries and recovery in a single trace view.